Method for optimizing the extraction process of multi-component rare earth mixtures and related devices

Abstract

The application discloses a multi-component rare earth mixture extraction process optimization method and a related device, relates to the technical field of process industry process design, and comprises the following steps: processing a target multi-component rare earth mixture, and determining a plurality of theoretical process packages; each theoretical process package comprises a set of theoretical process parameters; each theoretical process parameter is amplified to obtain a plurality of sets of actual process parameters; global optimization is performed based on an improved multi-objective differential evolution algorithm, a multi-objective optimization function and actual process alternative schemes to obtain a non-dominated Pareto optimal process scheme set; and based on preset indexes, all alternative schemes in the optimal process scheme set are evaluated to screen out a final recommended scheme, which is used for guiding engineering design of a multi-component rare earth mixture extraction production line. The application can systematically and efficiently complete process optimization and parameter optimization of a multi-component rare earth mixture extraction process, and comprehensively improves economic benefits and resource utilization rate.

Description

Technical Field

[0001] This application relates to the field of process industry process design technology, and in particular to a method and related apparatus for optimizing a multi-component rare earth mixture extraction process. Background Technology

[0002] Rare earth elements are a strategically critical mineral resource for the nation, and their efficient separation is crucial for ensuring the development of new materials, new energy, and cutting-edge technology industries. Intelligent process design for the extraction of multi-component rare earth mixtures has become an urgent industry need. Current research has attempted to introduce optimization algorithms into intelligent process design to improve design efficiency and quality. However, existing solutions still have significant shortcomings, mainly in the following aspects: Firstly, existing methods often employ simplified single-objective optimization models or combine multiple objectives through linear weighting, failing to fully reflect the complex trade-offs between process cost and recovery rate in actual production. Furthermore, the established optimization models are usually based on idealized theoretical parameters, neglecting engineering factors in actual production processes, leading to significant deviations between optimization results and actual production indicators, thus limiting their guiding significance. Secondly, existing methods often employ standard algorithms or intelligent optimization methods improved from single strategies. However, these methods often suffer from slow convergence speeds, susceptibility to local optima, and poor solution set diversity, hindering the overall performance improvement of process design. Summary of the Invention

[0003] The purpose of this application is to provide a method and related apparatus for optimizing the extraction process of multi-component rare earth mixtures, which can automatically select the optimal combination of extraction steps and process parameters by comprehensively considering process cost and resource utilization.

[0004] To achieve the above objectives, this application provides the following solution.

[0005] In a first aspect, this application provides an optimized method for the extraction process of multi-component rare earth mixtures, comprising the following steps: The target multi-component rare earth mixture is processed to determine multiple theoretical process packages. Each theoretical process package includes a set of theoretical process parameters and a corresponding theoretical extraction step. The theoretical process parameters include at least the theoretical number of extraction stages, the theoretical number of washing stages, the theoretical extraction rate, and the theoretical washing rate.

[0006] Each set of theoretical process parameters is scaled up to obtain multiple sets of actual process parameters. The actual process parameters include at least the actual number of extraction stages, the actual number of washing stages, the actual volume of the extract liquid, and the actual volume of the washing liquid.

[0007] A global optimization solution is obtained by using an improved multi-objective differential evolution algorithm, a multi-objective optimization function, and multiple practical process alternatives to obtain a non-dominated Pareto optimal process solution set. Each practical process alternative includes a set of practical process parameters and a corresponding theoretical extraction step; different practical process alternatives include different practical process parameters. The population update step in the improved multi-objective differential evolution algorithm adopts a three-mutation adaptive strategy. The non-dominated Pareto optimal process solution set includes at least one of the practical process alternatives. The multi-objective optimization function is a function established with the objectives of minimizing the total process design cost and maximizing the monthly recovery rate.

[0008] Based on preset quality indicators for multi-component rare earth products, each of the actual process alternatives in the non-dominated Pareto optimal process scheme set is evaluated, and a final recommended scheme is selected. The final recommended scheme includes a set of actual process parameters and corresponding theoretical extraction steps. The final recommended scheme is used to guide the engineering design of the target multi-component rare earth mixture extraction production line.

[0009] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for optimizing the extraction process of multi-component rare earth mixtures.

[0010] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method for optimizing the extraction process of multi-component rare earth mixtures.

[0011] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for optimizing the extraction process of multi-component rare earth mixtures.

[0012] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a method and related apparatus for optimizing the extraction process of multi-component rare earth mixtures. For each actual process alternative, a dual-objective optimization function is established with the core objectives of "minimizing the total process design cost" and "maximizing the monthly recovery rate." This dual-objective optimization function directly corresponds to the key economic and technical indicators in production, overcoming the shortcomings of existing methods with a single objective. More importantly, the input parameters in this dual-objective optimization function are all derived from actual process parameters that have been "scaled up," introducing an engineering correction mechanism for actual production losses and equipment efficiency. This makes the optimization model closely fit the real production scenario, significantly improving the engineering feasibility and guiding value of the optimization results. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is an application environment diagram of an optimization method for extraction process of multi-component rare earth mixtures in one embodiment of this application; Figure 2 A schematic flowchart illustrating an optimized extraction process for a multi-component rare earth mixture provided in an embodiment of this application; Figure 3 A Pareto front solution set diagram of a multi-objective function for an extraction process provided in an embodiment of this application; Figure 4 This is a schematic diagram of the rare earth extraction process. Figure 5 This is a schematic diagram of a rare earth extraction and separation process provided in another embodiment of this application; Figure 6 This is a flowchart of a multi-objective differential evolution algorithm provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.

[0015] Attached image labels: 102 terminal, 104 server. Detailed Implementation

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0017] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] The multi-component rare earth mixture extraction process optimization method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server. Terminal 102 can process the target multi-component rare earth mixture, determine multiple theoretical process packages, and send these packages to server 104. Each theoretical process package includes a set of theoretical process parameters and a corresponding theoretical extraction step. Server 104 amplifies each set of theoretical process parameters to obtain multiple sets of actual process parameters; based on an improved multi-objective differential evolution algorithm, a multi-objective optimization function, and multiple actual process alternatives, it performs global optimization to obtain a non-dominated Pareto optimal process solution set. Each actual process alternative includes a set of actual process parameters and corresponding theoretical extraction steps. Different actual process alternatives include different actual process parameters. Based on the preset quality indicators of multi-component rare earth products, each actual process alternative in the non-dominated Pareto optimal process scheme set is evaluated, and the final recommended scheme is selected. The server 104 can feed back the obtained final recommended scheme to the terminal 102. In addition, in some embodiments, the multi-component rare earth mixture extraction process optimization method can also be implemented by the server 104 or the terminal 102 alone. For example, the terminal 102 can process the target multi-component rare earth mixture to determine multiple theoretical process packages and process multiple theoretical process packages, or the server 104 can obtain multiple theoretical process packages from the data storage system and process multiple theoretical process packages.

[0019] The terminal 102 can be, but is not limited to, various desktop computers, laptops, and IoT devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0020] The multi-component rare earth mixture extraction process optimization method provided in this application can achieve efficient, low-cost, and high-yield design and production guidance for the multi-component rare earth mixture extraction process. Addressing technical issues such as product quality, unit cost, organic phase storage tank volume, and rare earth storage tank volume in the rare earth extraction production process, and taking into account existing equipment conditions, process integration, and technical requirements, this application proposes a multi-component rare earth mixture extraction process optimization method, optimizing the process flow and parameters of the rare earth extraction process.

[0021] In one exemplary embodiment, such as Figure 2As shown, a method for optimizing the extraction process of multi-component rare earth mixtures is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 204.

[0022] Step 201: Process the target multi-component rare earth mixture to determine multiple theoretical process packages. Each theoretical process package includes a set of theoretical process parameters and a corresponding theoretical extraction step. The theoretical process parameters include at least the theoretical number of extraction stages, the theoretical number of washing stages, the theoretical extraction rate, and the theoretical washing rate.

[0023] Step 202: Scale up each set of theoretical process parameters to obtain multiple sets of actual process parameters. The actual process parameters include at least the actual number of extraction stages, the actual number of washing stages, the actual volume of the extract liquid, and the actual volume of the washing liquid.

[0024] Step 203 involves a global optimization solution based on an improved multi-objective differential evolution algorithm, a multi-objective optimization function, and multiple practical process alternatives, resulting in a non-dominated Pareto optimal process solution set. Each practical process alternative includes a set of practical process parameters and a corresponding theoretical extraction process; different practical process alternatives include different practical process parameters. The population update step in the improved multi-objective differential evolution algorithm employs a three-mutation adaptive strategy. The non-dominated Pareto optimal process solution set includes at least one of the practical process alternatives. The multi-objective optimization function is a function established with the objectives of minimizing the total process design cost and maximizing the monthly recovery rate.

[0025] Step 204: Based on the preset quality indicators for multi-component rare earth products, evaluate each of the actual process alternatives in the non-dominated Pareto optimal process scheme set, and select the final recommended scheme. The final recommended scheme includes a set of actual process parameters and corresponding theoretical extraction steps. The final recommended scheme is used to guide the engineering design of the target multi-component rare earth mixture extraction production line.

[0026] By implementing steps 201 to 204 above, the target multi-component rare earth mixture is processed to generate multiple theoretical process schemes. The theoretical parameters are transformed into actual process parameters through a process scale-up strategy. An improved multi-objective differential evolution algorithm is used for global optimization to obtain a Pareto optimal scheme set that balances process cost and recovery rate. Finally, the optimal design is selected based on economic benefit evaluation indicators. This effectively overcomes the shortcomings of traditional empirical design methods in terms of multi-objective and multi-process coupled optimization capabilities. It can systematically and efficiently complete the process optimization and parameter optimization of the multi-component rare earth mixture extraction process, and achieve a comprehensive improvement in economic benefits and resource utilization.

[0027] In another exemplary embodiment of this application, in step 201 above, due to the rare earth extraction process design, different initial process conditions are set to generate different processes. Through cascade extraction mechanism analysis, multiple theoretical extraction procedures are obtained. Based on the rare earth extraction process flow, cascade extraction model, and theoretical extraction procedures, the target multi-component rare earth mixture is processed to obtain multiple sets of theoretical process parameters. Based on the multiple theoretical extraction procedures and multiple sets of theoretical process parameters, multiple theoretical process packages are determined. Each theoretical process package includes a set of theoretical process parameters and a corresponding theoretical extraction procedure. The theoretical process parameters include at least the theoretical number of extraction stages, the theoretical number of washing stages, the theoretical extraction amount, the theoretical washing amount, and the purity of the products at both ends (organic phase outlet and aqueous phase outlet).

[0028] In another exemplary embodiment of this application, in step 202 above, considering the actual separation efficiency of the process, each set of theoretical process parameters is scaled up. Through a further scale-up strategy, multiple sets of process design parameters that conform to the actual process are obtained, i.e., actual process parameters. The actual process parameters include at least the actual number of extraction stages, the actual number of washing stages, the actual volume of the extraction liquid, and the actual volume of the washing liquid. Specifically, the rare earth extraction process parameter design uses the cascade extraction theoretical formula to obtain theoretical process parameters, and then obtains various process parameters that conform to the production process through actual scale-up.

[0029] In another exemplary embodiment of this application, the amplification process in step 202 is specifically as follows: based on the extractant concentration, detergent concentration, and one-step amplification factor, the theoretical extraction amount and the theoretical washing amount are processed respectively to obtain the actual extractant flow rate and the actual detergent flow rate; wherein, the one-step amplification factor is the ratio of the actual processed liquid volume per minute to the theoretical processed liquid volume per minute.

[0030] In another exemplary embodiment of this application, step 203 is replaced by steps 2031-2032: Step 2031: Based on the Pareto elite strategy and lens imaging reverse learning, the chaotic initialization method is used to process the initial solution space consisting of multiple actual process alternatives to obtain an initial solution set with enhanced diversity, and the initial solution set is used as the starting population of the improved multi-objective differential evolution algorithm.

[0031] Step 2032: Based on the improved multi-objective differential evolution algorithm, multi-objective optimization function and the initial population, a non-dominated Pareto optimal process scheme set is obtained.

[0032] An improved multi-objective differential evolution algorithm is employed for global optimization. This algorithm effectively handles high-dimensional, nonlinear optimization problems with multiple alternatives, ultimately outputting a non-dominated Pareto optimal process solution set. This set provides a series of high-quality solutions that balance cost and recovery rate objectives, laying a solid foundation for subsequent decision-making based on economic indicators and achieving a complete closed loop from optimization to engineering recommendation.

[0033] In another exemplary embodiment of this application, step 2031 above is replaced by the following steps: Population initialization is achieved using a chaotic space cubic mapping relationship. Specifically, in randomly generated chaotic variables, multiple iterations and recombinations are performed to form a combination of individual populations. Furthermore, initial populations with maximum and minimum boundaries are generated in the chaotic space and merged. A non-dominated sorting method is used to select the initial population.

[0034] In another exemplary embodiment of this application, step 2031 specifically involves optimizing the diversity of the chaotic initialization population during the initialization process. This optimization utilizes the sensitivity of chaos to initial conditions, allowing for bounded, random, regular, and non-repeating traversal of all states. Furthermore, it employs a chaotic initialization method based on the lens imaging inverse learning strategy to generate two initial populations containing opposite solutions, thereby improving the diversity of the initialization population. To further enhance the uniformity and quality of the initial population, this step integrates a optimal point set generation method with the chaotic initialization method to collaboratively construct the initial population.

[0035] In another exemplary embodiment of this application, step 2032 is replaced by steps 2033-2037.

[0036] The population is initialized based on the elite mirroring. A maximum boundary population and a minimum boundary population are generated in the solution space, and the maximum boundary population and the minimum boundary population are merged into an initial merged population. The initial merged population is sorted in a non-dominated manner, and each individual is assigned to a different non-dominated level. Individuals in the same non-dominated level are sorted according to the crowding of individuals in the population, and the optimal initial population is selected based on the sorting results as the current population.

[0037] Step 2033: Using a multi-objective optimization function, calculate the objective function value corresponding to each actual process alternative in the current population, and the corresponding total process cost. and monthly recovery rate of processes ; in, The total cost of the multi-component rare earth extraction production process; The monthly recovery rate for each process.

[0038] Step 2034: Sort the individuals in the current population in a non-dominated order according to the objective function value, and filter and store the Pareto optimal solution by calculating and comparing the crowding values ​​of the individuals in the population.

[0039] Step 2035: Determine whether the objective function value corresponding to each actual process alternative in the current population satisfies the preset termination condition, and obtain the first judgment result; the preset termination condition is that the number of iterations reaches the preset maximum number of iterations; when the number of iterations corresponding to the current population is 1, the current population is the starting population.

[0040] Step 2036: If the first judgment result is yes, then the non-dominated solution set in the current population is taken as the set of non-dominated Pareto optimal process solutions. The non-dominated solution set in the current population is a set consisting of all actual process alternatives in the current population that are not dominated by other solutions.

[0041] Step 2037: If the first judgment result is negative, then perform a three-mutation adaptive strategy on each actual process alternative in the current population to obtain a mutation vector population, and obtain a new generation population based on the mutation vector population, and update the new generation population to the current population, and return to step 2033.

[0042] In the saved Pareto solution, process parameters such as feed liquid composition, number of extraction tank stages, number of washing tank stages, and maximum extraction rate are obtained as the global optimal solution for the multi-component rare earth extraction process, thereby achieving multi-objective optimization design of the extraction process with corresponding total process cost J and monthly recovery rate E.

[0043] A new population and individuals are generated, and the non-dominated sorting and crowding value calculation are performed again. The Pareto algorithm is then used to find the optimal solution. In the set of optimal solutions, the solution that satisfies the minimum process cost and the highest monthly recovery rate is selected as the global optimal solution. The process parameters at this point, such as the number of extraction stages, the number of washing stages, the maximum extraction rate, and the feed concentration, are used as the optimal design parameters to achieve the process design of the multi-component rare earth extraction process.

[0044] In another exemplary embodiment of this application, the Pareto principle combined with an improved differential evolution algorithm is used to solve the multi-objective optimization problem of process design for multi-component rare earth extraction, specifically including the following process: Population initialization: The initial population is constructed using elite mirroring and chaotic initialization methods. Each individual represents a specific set of process design parameters (i.e., actual process alternatives). Objective function calculation: Based on the process performance indicators (total cost and monthly recovery rate), calculate the objective function value for each individual in the current population; Non-dominated ranking and crowding calculation: The population is non-dominated based on Pareto dominance relations, and the crowding of each individual is calculated to evaluate the diversity and convergence of the solution set. External archive update: Store the non-dominated solutions (Pareto optimal solutions) in the current population into the external archive as a set of candidate optimal solutions; Adaptive Mutation and Crossover: A three-mutation adaptive strategy (DE / current-to-pbest / 1, DE / best / 1, DE / rand / 1) is used to mutate the population to generate a mutated vector population; then adaptive crossover is performed to generate an experimental vector population. Elite selection and population update: The experimental vector population is merged with the current population, and elite selection is performed based on non-dominated ranking and crowding distance to select outstanding individuals to form a new generation of population; Iteration termination check: Determine if the preset maximum number of iterations (G=100) has been reached. If not, continue iterating; if so, terminate the iteration. Output Pareto optimal solution set: The final output is the non-dominated solution set stored in the external archive, namely the Pareto front solution set, which provides multiple globally optimal solutions for process design.

[0045] The Pareto front solution set diagram of the multi-objective function in the extraction process is shown below. Figure 3 As shown, theoretically, Figure 3 Each candidate solution in the Pareto front solution set shown can be used as the final process parameter design scheme.

[0046] In another exemplary embodiment of this application, in step 2037 above, during the crossover mutation process, an adaptive parameter update method is used to set the scaling factor F, crossover probability CR, and population size NP value to meet the different requirements of each parameter at different evolutionary stages, thereby better improving the algorithm's convergence and solution diversity. Specifically, in the adaptive crossover processing, an adaptive crossover probability dynamic adjustment mechanism is introduced, and a uniform crossover operation method is used to more finely balance the algorithm's exploration and development capabilities. The adaptive crossover processing plays a "recombination" role, using the potential "mutated vector population" generated by the "three-mutation adaptive strategy processing" to exchange genes with the "current population" (parent generation) according to dynamically adjusted rules, generating a more diverse and potentially better "experimental vector population." This provides high-quality candidate solutions for the subsequent "elite selection processing based on non-dominated sorting and crowding distance," aiming to better balance global search (exploration) and local optimization (development), thereby more effectively approaching the Pareto optimal front of the multi-objective optimization problem.

[0047] In another exemplary embodiment of this application, the three-variation adaptive strategy specifically includes: The three strategies are DE / current-to-pbest / 1, DE / best / 1, and DE / rand / 1. A combination of these three strategies is defined as a three-mutation adaptive strategy to balance the convergence speed and accuracy of the algorithm. Each individual represents a candidate solution for a given actual process; the fitness of each individual is the objective function value corresponding to that candidate solution.

[0048] In another exemplary embodiment of this application, the calculation process of the three-variation adaptive strategy specifically includes: ; ; ; ; in, Mutation vectors generated for the DE / current-to-pbest / 1 strategy; Mutation vectors generated for the DE / best / 1 strategy; The mutation vector generated for the DE / rand / 1 strategy; This is the fusion mutation vector; The mutation vector; This is the scaling factor; F1, F2, F3 These are the variation scale control factors for the DE / current-to-pbest / 1 strategy, the DE / best / 1 strategy, and the DE / rand / 1 strategy, respectively. , , , and A random individual in the Gth generation population; This refers to individuals with relatively good fitness within the current population. This refers to the individual with the best fitness in the current population. Let i be the i-th individual in the G-th generation population.

[0049] In another exemplary embodiment of this application, such as Figure 4 The diagram illustrates the rare earth extraction process, describing a cascade fractionation extraction process with n-stage extraction and m-stage washing. In the actual extraction process design, the differences in extracted elements are fully considered, leading to further optimization of the rare earth extraction process parameters. This optimization process mainly includes (1) designing the extraction process steps for multi-component rare earth mixtures; (2) determining the optimal extraction rate and the number of extraction and washing stages for key extraction parameters; and (3) an improved multi-objective differential evolution algorithm.

[0050] The extraction process for multi-component rare earth mixtures varies depending on the specific steps, extraction procedures, and feeding methods. This leads to variations in extraction yield, washing volume, wastewater volume, and extraction results, resulting in significant differences in final production costs. Separation processes, such as... Figure 5 As shown in Table 1, an example of a multi-component rare earth mixture extraction process is presented. This process is designed based on different element cutting positions and feeding methods. Specifically, taking the separation of four rare earth elements (La / Ce / Pr / Nd) as an example, it includes the following five process schemes: Table 1. Process steps corresponding to different cutting methods

[0051] The numbers 1-3 indicate the cutting positions of the elements.

[0052] Specifically, the process flow diagram in Table 1 is given. The first process: First, the La element in the La / Ce, Pr, and Nd group is separated. Ce, Pr, and Nd then proceed to the next separation process. Similarly, this is further divided into two processes: Process A, Ce / Pr, Nd: The rare earth element Ce is separated first, followed by the separation of Pr / Nd. Process B, or Ce / Pr / Nd: Nd is separated first, followed by the further separation of Ce / Pr.

[0053] The second process: La, Ce, Pr / Nd. First, Nd is separated. Then, the La, Ce, and Pr separation process begins, also divided into step C, La / Ce, Pr. First, La is separated, then Ce / Pr is separated. Step D, La, Ce / Pr. First, Pr is separated, then La / Ce is separated.

[0054] The third process, La, Ce / Pr, and Nd, first separates the La, Ce / Pr, and Nd elements, and then proceeds to the next separation process; further, two processes are needed to separate the four elements respectively.

[0055] The more rare earth elements present, the more complex the separation process becomes, and the stronger the coupling relationship between the parameters of each process. The choice of different process designs is crucial to the industrial application of multi-component rare earth mixture processes. Considering the design cost of each extraction tank and the corresponding supporting facilities, in the production process design, the fewer the extraction steps and extraction tank stages, the better, while ensuring product purity.

[0056] In another exemplary embodiment of this application, step 202 is described in detail, which considers the actual process separation efficiency and amplifies each set of theoretical process parameters. Through a further amplification strategy, multiple sets of process design parameters that conform to the actual process are obtained, i.e., the specific process of the actual process parameters.

[0057] Through formula With formula The purification factors a and b of product A collected from the organic phase outlet and product B collected from the aqueous phase outlet are calculated; where a is the purification factor of product A collected from the organic phase outlet and b is the purification factor of product B collected from the aqueous phase outlet. The preset target purity for product A collected from the organic phase outlet; The preset target purity for product B collected from the aqueous phase outlet; The mass fraction of product A extracted from the organic phase outlet; This represents the mass fraction of product B collected from the aqueous phase outlet. After obtaining the purification factors a and b for product A collected from the organic phase outlet and product B collected from the aqueous phase outlet, it is necessary to calculate the outlet yield of product A collected from the organic phase outlet based on a and b. and the export yield of product B extracted from the aqueous phase outlet. .

[0058] The formula for calculating the export yield of product A collected from the organic phase outlet is as follows: ; The formula for calculating the export yield of product B extracted from the aqueous phase outlet is as follows: .

[0059] In actual production, the extraction efficiency will lag. To ensure product purity requirements, the number of extraction and washing stages required will be further increased based on the theoretical design.

[0060] Based on the actual separation efficiency, and using the average separation coefficient of the washing section... Considering the actual separation energy efficiency of the extraction process, an energy efficiency coefficient is added. The average separation coefficient of the extraction section was obtained. Based on the aforementioned process parameters and energy efficiency separation coefficient, the mixed extraction ratio of the extraction section and the washing section is further obtained. , ,in, n This represents the actual number of stages in the extraction segment. m This represents the actual number of stages in the washing section.

[0061] Furthermore, the corrected extraction amount and the corrected washing amount can be obtained by calculating using the following formula: ; in, This is the corrected extraction amount; ; in, This is the corrected washing volume.

[0062] Given the concentration of the feed solution Extractant concentration Detergent concentration Under the conditions of calculation theory, with This refers to the feed rate, specifically the volume of liquid feed per minute. Extract volume and washing liquid volume .

[0063] Due to separation efficiency issues in actual extraction production, industrial extraction typically employs a "one-step scale-up" strategy, assuming an actual feed volume processed per minute of [volume value missing]. This allows us to obtain a one-step magnification factor. This further yields the actual process parameters conforming to the production process after a one-step scale-up: actual extract volume. and the actual volume of washing liquid The actual volume of the extract can also be expressed as... The actual volume of the washing liquid can also be expressed as: .

[0064] In another exemplary embodiment of this application, the cost of extractant consumption and the cost of detergent consumption are directly proportional to the flow rate of the organic phase and the flow rate of the acid solution, respectively, so their daily consumption can be determined based on the flow rate. In the first objective function, the expression for the total cost of the current process is: Among them, the daily consumption cost Extractant consumption cost Detergent consumption cost , The time consumed by the daily mass flow rate of the feed liquid, i.e. Fixed costs (including the cost of the extraction tank and other fixed costs on average at each stage of the tank). , This is the extractant consumption coefficient. This is the detergent consumption coefficient. This is the unit price of the extractant. This is the unit price of the detergent. This is to average out other fixed costs at each stage of the tank.

[0065] In another exemplary embodiment of this application, the formula for calculating the monthly export output of organic phase products is as follows: ; The formula for calculating the monthly export volume of aqueous products is as follows: .

[0066] In another exemplary embodiment of this application, the multi-objective optimization function in step 203 includes a first objective function and a second objective function.

[0067] The expression for the first objective function is: ,in: ; in, This represents the total cost of the multi-component rare earth extraction production process; there are n processes in total. The cost of the i-th process is calculated based on the concentration of the feed solution, the actual volume of feed solution processed per minute, the extractant consumption coefficient, the actual volume of the extractant, the unit price of the extractant, the detergent consumption coefficient, the actual volume of the detergent, the unit price of the detergent, the average other fixed costs on each stage of the tank, the actual number of extraction stages, and the actual number of washing stages.

[0068] The expression for the second objective function is: ,in: ; in, The monthly recovery rate for each process; This represents the actual monthly output of a single process. This represents the monthly consumption of a single process. The actual monthly output of the process is calculated based on the actual volume of liquid processed per minute, the concentration of the liquid, the mass fraction of product A collected from the organic phase outlet, the outlet yield of product A collected from the organic phase outlet, the preset target purity of product A collected from the organic phase outlet, the time consumed by the daily liquid mass flow rate, the mass fraction of product B collected from the aqueous phase outlet, the outlet yield of product B collected from the aqueous phase outlet, and the preset target purity of product B collected from the aqueous phase outlet. The outlet yield of product A collected from the organic phase outlet and the outlet yield of product B collected from the aqueous phase outlet are calculated based on the purification multiples of product A collected from the organic phase outlet and product B collected from the aqueous phase outlet.

[0069] In another exemplary embodiment of this application, the calculation of the output of the rare earth extraction workshop is an important part of production management, which is directly related to the economic benefits and resource utilization rate of the enterprise. In the second objective function... The calculation formula is as follows: ; This represents the monthly export volume of organic phase products. This refers to the monthly export volume of products with aqueous phases.

[0070] In another exemplary embodiment of this application, the specific process of establishing the multi-objective optimization function in step 203 above is as follows: In actual production, the purity of the final product from extraction and separation is the primary indicator. The process comprehensively considers the proportions and consumption of materials such as feed liquid, extractant, and detergent required for extraction, as well as the control of saponification during the proportioning process. If these parameters are exceeded, corrosion and damage to the extraction tank during extraction will cause additional production costs, and in more serious cases, even interrupt the product production process. Therefore, to achieve normal production while minimizing the total cost of the entire process design, a first objective function and a second objective function are established based on the design of the rare earth extraction process parameters.

[0071] The first objective function is the objective function for the total cost of the established process design. Specifically, the consumption cost is determined based on the amount of extractant and detergent required in the rare earth production process, and the total production design cost of the multi-component rare earth mixture extraction process is obtained by adding the construction cost of each process flow of rare earth extraction.

[0072] The second objective function is the established objective function for the monthly recovery rate. The monthly recovery rate of the rare earth extraction process is an important indicator for measuring extraction efficiency and resource utilization. Under sufficient extraction and separation, the actual monthly output of each process can be obtained. The second objective function is constructed based on the monthly recovery rate of each process and the monthly consumption of each process.

[0073] To minimize the total cost of process design And maximize monthly recovery rate To optimize the target, the monthly recovery rate of rare earth extraction process can be effectively improved, production costs can be reduced, and both economic benefits and resource utilization efficiency can be improved.

[0074] In another exemplary embodiment of this application, a specific implementation plan and testing and verification process of the improved multi-objective differential evolution algorithm are described: An improved multi-objective differential evolution algorithm is constructed by combining a non-dominated sorting strategy with crowding distance calculation to globally optimize actual process alternatives. Considering the interaction relationships between objective functions, the improved multi-objective differential evolution algorithm is used to obtain a non-dominated Pareto optimal process scheme set using Pareto dominance relations, and the values ​​of each optimization sub-objective function are weighed to obtain the objective function value closest to the optimum.

[0075] The improved multi-objective differential evolution algorithm first completes the setting of the corresponding differential evolution algorithm parameters (population size, mutation factor, crossover probability), then sorts the archive set size, crowding distance parameters, and searches for the optimal solution according to the objective function. Its flowchart is as follows: Figure 6 As shown.

[0076] Specifically, a non-dominated Pareto optimal process scheme set is obtained by globally optimizing the improved multi-objective differential evolution algorithm, the multi-objective optimization function, and the actual process alternatives. Each actual process alternative includes a set of actual process parameters and a corresponding theoretical extraction step. The non-dominated Pareto optimal process scheme set includes at least one of the actual process alternatives. The multi-objective optimization function is established with the objectives of minimizing the total process design cost and maximizing the monthly recovery rate. Through the improved multi-objective differential evolution algorithm, the separation of elements (e.g., La / Ce / Pr / Nd) in the target multi-component rare earth mixture can be achieved, and the separation is consistent with the actual extraction process design, yield, and cost, thus achieving the goal of minimizing quality indicators and costs.

[0077] To construct and validate the improved multi-objective differential evolution algorithm, classic multi-objective test functions (including the Zitzler-Deb-Thiele series, Deb-Thiele-Laumanns-Zitzler series, and WFG series) were used to evaluate the convergence and diversity of the improved algorithm and verify its effectiveness. Furthermore, the algorithm's superiority was evaluated by solving three performance metrics (IGD, GD) to ensure its robustness before practical optimization.

[0078] Five variables with strong correlation in the extraction process settings—including the number of tank stages, raw material composition, and extraction rate—were selected as input variables. The improved multi-objective differential evolution algorithm of this application was used to design and optimize the product recovery rate and cost at both ends, comparing it with general MSADE, NSGA-II, GA, MOPSO, and MODE algorithms. The performance test results of the improved multi-objective differential evolution algorithm are shown in Table 2. The following five typical optimization algorithm test functions were used to test the search ability and global optimization ability of the improved algorithm to escape local convergence.

[0079] Table 2 Comparison of Algorithm Performance Test Results

[0080] In another exemplary embodiment of this application, a set of non-dominated Pareto optimal process solutions is obtained through step 203 above. The boundary or surface formed by the non-dominated solutions in the target space is called the Pareto Front. The Pareto Front diagram is a graph used to visualize the distribution of these non-dominated solutions in the multidimensional target space.

[0081] The actual extraction process involves two feeding methods: aqueous phase and organic phase. Specifically, taking the aqueous phase feeding method as an example, an improved differential evolution algorithm is used to solve the rare earth extraction process based on two objective functions: cost and monthly recovery rate. The actual extraction process involves two feeding methods: aqueous phase and organic phase. Specifically, with a population size N=100, dimension D=5, and maximum iteration count G=100, one of the sub-process design schemes is shown in Table 3. Table 3 Process Design Scheme

[0082] Similarly, other sub-processes can also obtain design schemes using the same method, and finally, the optimal process scheme is selected by combining production costs and monthly recovery rate targets.

[0083] Specifically, each set of solutions represents a feasible process scheme obtained after optimization. However, the actual design of the process parameters for the extraction of multi-component rare earth mixtures only requires one set of solutions as the final desired scheme. Therefore, in the set of non-dominated Pareto optimal process schemes, the ratio of rare earth element yield to corresponding cost during extraction is used as a measure of economic benefit and as an evaluation index for candidate solutions. The larger the ratio, the higher the economic benefit. The candidate solution with the largest ratio in the set of non-dominated Pareto optimal process schemes is selected as the optimal process parameter design, as shown in Table 4. In other words, based on the preset quality indicators for multi-component rare earth products, each actual process alternative scheme in the set of non-dominated Pareto optimal process schemes is evaluated, and the final recommended scheme is selected to achieve the optimal design of process parameters for multi-component rare earth mixtures. The final recommended scheme includes a set of actual process parameters and corresponding theoretical extraction steps. The final recommended scheme is used to guide the engineering design of the multi-component rare earth mixture extraction production line.

[0084] Table 4 shows the corresponding process parameters under the optimization results.

[0085] The above method optimizes the design of process parameters for production processes, and designs the steps and process parameters suitable for the element separation process of multi-component rare earth mixtures. Simultaneously, an improved multi-objective differential evolution algorithm-based process optimization method is proposed. This method uses the total cost of the process design at both ends of the product chain and the monthly recovery rate as output objectives. The improved multi-objective differential evolution algorithm is used to globally optimize the actual process alternatives, obtaining the optimal combination of process parameters for different steps. This achieves comprehensive optimization of the process design for different steps in the production process, meeting the design requirements for the extraction and separation process of multi-component rare earth mixtures.

[0086] In another exemplary embodiment of this application, the improved multi-objective differential evolution algorithm is compared with other algorithms on a test function to verify its effectiveness. Then, the improved multi-objective differential evolution algorithm is used to globally optimize the actual process alternatives (multi-objective production process design) to obtain the optimal combination of process parameters. Finally, taking an actual extraction production process as an example, the effectiveness of the proposed improved multi-objective differential evolution algorithm for rare earth extraction process and process parameter optimization is verified, predicting and guiding the actual process production.

[0087] This application also provides an application scenario in which the above-mentioned optimization method for the extraction process of multi-component rare earth mixtures is applied. Specifically, the optimization method for the extraction process of multi-component rare earth mixtures provided in this embodiment can be applied to the planning and process design of new production lines in rare earth extraction and separation plants. This scenario includes the process scheme design stage, the process parameter optimization stage, and the scheme decision-making and implementation stage. The optimization method for the extraction process of multi-component rare earth mixtures provided in this embodiment belongs to the core optimization and decision-making stage in the process scheme design stage.

[0088] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores multiple theoretical process packages. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements an optimization method for a multi-component rare earth mixture extraction process.

[0089] Those skilled in the art will understand that Figure 7 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0090] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0091] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0092] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use and processing of the relevant data are carried out in compliance with the relevant data protection laws and policies of the country where the location is located, and with the authorization granted by the owner of the corresponding device.

[0093] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0094] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0095] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0096] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An optimization method for the extraction process of multi-component rare earth mixtures, characterized in that, The optimization method for the extraction process of the multi-component rare earth mixture includes: The target multi-component rare earth mixture is processed to determine multiple theoretical process packages; each theoretical process package includes a set of theoretical process parameters and a corresponding theoretical extraction step; the theoretical process parameters include at least the theoretical number of extraction stages, the theoretical number of washing stages, the theoretical extraction rate, and the theoretical washing rate. Each set of theoretical process parameters is scaled up to obtain multiple sets of actual process parameters; the actual process parameters include at least the actual number of extraction stages, the actual number of washing stages, the actual volume of the extract liquid, and the actual volume of the washing liquid. A global optimization solution is obtained by using an improved multi-objective differential evolution algorithm, a multi-objective optimization function, and multiple practical process alternatives to obtain a non-dominated Pareto optimal process solution set. Each practical process alternative includes a set of practical process parameters and a corresponding theoretical extraction process; different practical process alternatives include different practical process parameters. The population update step in the improved multi-objective differential evolution algorithm adopts a three-mutation adaptive strategy. The non-dominated Pareto optimal process solution set includes at least one of the practical process alternatives. The multi-objective optimization function is a function established with the objectives of minimizing the total process design cost and maximizing the monthly recovery rate. Based on the preset quality indicators of multi-component rare earth products, each of the actual process alternatives in the non-dominated Pareto optimal process scheme set is evaluated, and the final recommended scheme is selected. The final recommended scheme includes a set of actual process parameters and corresponding theoretical extraction steps. The final recommended scheme is used to guide the engineering design of the target multi-component rare earth mixture extraction production line.

2. The method for optimizing the extraction process of multi-component rare earth mixtures according to claim 1, characterized in that, A global optimization solution is obtained by using an improved multi-objective differential evolution algorithm, a multi-objective optimization function, and multiple practical process alternatives, resulting in a non-dominated Pareto optimal process solution set, specifically including: A chaotic initialization method based on Pareto elite strategy and lens imaging reverse learning is used to process the initial solution space consisting of multiple practical process alternatives to obtain an initial solution set with enhanced diversity. This initial solution set is then used as the starting population for the improved multi-objective differential evolution algorithm. Based on the improved multi-objective differential evolution algorithm, multi-objective optimization function, and the initial population, a set of non-dominated Pareto optimal process schemes is obtained.

3. The method for optimizing the extraction process of multi-component rare earth mixtures according to claim 2, characterized in that, Based on the improved multi-objective differential evolution algorithm, multi-objective optimization function, and the initial population, a set of non-dominated Pareto optimal process schemes is obtained, specifically including: The population is initialized based on the elite mirror. A maximum boundary population and a minimum boundary population are generated in the solution space, and the maximum boundary population and the minimum boundary population are merged into an initial merged population. The initial merged population is sorted by non-dominated ordering, and each individual is assigned to a different non-dominated level. Individuals in the same non-dominated level are sorted according to the crowding of individuals in the population, and the optimal initial population is selected based on the sorting results as the current population. Using a multi-objective optimization function, the objective function value corresponding to each actual process alternative in the current population is calculated; The individuals in the current population are sorted non-dominated according to the objective function value, and the Pareto optimal solution is selected and stored by calculating and comparing the crowding values ​​of the individuals in the population. Determine whether the objective function value corresponding to each actual process alternative in the current population satisfies the preset termination condition to obtain the first determination result; the preset termination condition is that the number of iterations reaches the preset maximum number of iterations; when the number of iterations corresponding to the current population is 1, the current population is the starting population; If the first judgment result is yes, then the non-dominated solution set in the current population is taken as the set of non-dominated Pareto optimal process schemes; If the first judgment result is negative, then a three-mutation adaptive strategy is applied to each actual process candidate scheme in the current population to obtain a mutation vector population, and a new generation population is obtained based on the mutation vector population. The new generation population is then updated to the current population, and the process returns to the step of using a multi-objective optimization function to calculate the objective function value corresponding to each actual process candidate scheme in the current population.

4. The method for optimizing the extraction process of multi-component rare earth mixtures according to claim 1, characterized in that, The three-variation adaptive strategy specifically includes: DE / current-to-pbest / 1 strategy, DE / best / 1 strategy, and DE / rand / 1 strategy.

5. The method for optimizing the extraction process of multi-component rare earth mixtures according to claim 4, characterized in that, The calculation process of the three-variation adaptive strategy specifically includes: ； ； ； ； in, Mutation vectors generated for the DE / current-to-pbest / 1 strategy; Mutation vectors generated for the DE / best / 1 strategy; The mutation vector generated for the DE / rand / 1 strategy; This is the fusion mutation vector; This is the scaling factor; F 1 、F 2 、F 3 These are the variation scale control factors for the DE / current-to-pbest / 1 strategy, the DE / best / 1 strategy, and the DE / rand / 1 strategy, respectively. , , , and A random individual in the Gth generation population; This refers to individuals with relatively good fitness within the current population. This refers to the individual with the best fitness in the current population. Let i be the i-th individual in the G-th generation population.

6. The method for optimizing the extraction process of multi-component rare earth mixtures according to claim 1, characterized in that, The amplification process is specifically as follows: Based on the extractant concentration, detergent concentration, and one-step amplification factor, the theoretical extraction volume and the theoretical washing volume are processed to obtain the actual extractant flow rate and the actual detergent flow rate; wherein, the one-step amplification factor is the ratio of the actual processed liquid volume per minute to the theoretical processed liquid volume per minute.

7. The method for optimizing the extraction process of multi-component rare earth mixtures according to claim 1, characterized in that, The multi-objective optimization function includes a first objective function and a second objective function; The expression for the first objective function is: ,in: ； in, This represents the total cost of the multi-component rare earth extraction production process; there are n processes in total. The cost of the i-th process is calculated based on the concentration of the feed liquid, the actual volume of feed liquid processed per minute, the extractant consumption coefficient, the actual volume of the extractant, the unit price of the extractant, the detergent consumption coefficient, the actual volume of the detergent, the unit price of the detergent, the average other fixed costs on each stage of the tank, the actual number of extraction stages, and the actual number of washing stages. The expression for the second objective function is: ,in: ； in, The monthly recovery rate for each process; This represents the actual monthly output of a single process. This represents the monthly consumption of a single process. The actual monthly output of the process is calculated based on the actual volume of liquid processed per minute, the concentration of the liquid, the mass fraction of product A collected from the organic phase outlet, the outlet yield of product A collected from the organic phase outlet, the preset target purity of product A collected from the organic phase outlet, the time consumed by the daily liquid mass flow rate, the mass fraction of product B collected from the aqueous phase outlet, the outlet yield of product B collected from the aqueous phase outlet, and the preset target purity of product B collected from the aqueous phase outlet. The outlet yield of product A collected from the organic phase outlet and the outlet yield of product B collected from the aqueous phase outlet are calculated based on the purification multiples of product A collected from the organic phase outlet and product B collected from the aqueous phase outlet.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the method for optimizing the extraction process of multi-component rare earth mixtures according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for optimizing the extraction process of multi-component rare earth mixtures as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the method for optimizing the extraction process of multi-component rare earth mixtures as described in any one of claims 1-7.

Images